Article
Computer Science, Artificial Intelligence
Paolo Soda, Natascha Claudia D'Amico, Jacopo Tessadori, Giovanni Valbusa, Valerio Guarrasi, Chandra Bortolotto, Muhammad Usman Akbar, Rosa Sicilia, Ermanno Cordelli, Deborah Fazzini, Michaela Cellina, Giancarlo Oliva, Giovanni Callea, Silvia Panella, Maurizio Cariati, Diletta Cozzi, Vittorio Miele, Elvira Stellato, Gianpaolo Carrafiello, Giulia Castorani, Annalisa Simeone, Lorenzo Preda, Giulio Iannello, Alessio Del Bue, Fabio Tedoldi, Marco Ali, Diego Sona, Sergio Papa
Summary: This study investigates the use of artificial intelligence with chest X-ray scans and clinical data for the early identification of COVID-19 patients at risk, showing promising performance and potential for providing useful information in patient and hospital resource management.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Health Care Sciences & Services
Hyun Woo Lee, Hyun Jun Yang, Hyungjin Kim, Ue-Hwan Kim, Dong Hyun Kim, Soon Ho Yoon, Soo-Youn Ham, Bo Da Nam, Kum Ju Chae, Dabee Lee, Jin Young Yoo, So Hyeon Bak, Jin Young Kim, Jin Hwan Kim, Ki Beom Kim, Jung Im Jung, Jae-Kwang Lim, Jong Eun Lee, Myung Jin Chung, Young Kyung Lee, Young Seon Kim, Sang Min Lee, Woocheol Kwon, Chang Min Park, Yun-Hyeon Kim, Yeon Joo Jeong, Kwang Nam Jin, Jin Mo Goo
Summary: This study aimed to develop and validate a prediction model using chest radiography (CXR) and clinical variables to predict clinical outcomes in COVID-19 patients. The combined model using an AI model and clinical information showed good performance in predicting ARDS and need for oxygen supplementation in COVID-19 patients.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2023)
Article
Medicine, General & Internal
Joseph Bae, Saarthak Kapse, Gagandeep Singh, Rishabh Gattu, Syed Ali, Neal Shah, Colin Marshall, Jonathan Pierce, Tej Phatak, Amit Gupta, Jeremy Green, Nikhil Madan, Prateek Prasanna
Summary: This study aimed to predict mechanical ventilation requirement and mortality for COVID-19 patients using computed modeling of chest radiographs. Various machine learning classifiers were trained and evaluated, with radiomic features showing improvement in model predictions and aiding in physician decision making during the pandemic.
Article
Radiology, Nuclear Medicine & Medical Imaging
Paras Lakhani, J. Mongan, C. Singhal, Q. Zhou, K. P. Andriole, W. F. Auffermann, P. M. Prasanna, T. X. Pham, Michael Peterson, P. J. Bergquist, T. S. Cook, S. F. Ferraciolli, G. C. A. Corradi, M. S. Takahashi, C. S. Workman, M. Parekh, S. Kamel, J. Galant, A. Mas-Sanchez, E. C. Benitez, M. Sanchez-Valverde, L. Jaques, M. Panadero, M. Vidal, M. Culianez-Casas, D. Angulo-Gonzalez, S. G. Langer, Maria de la Iglesia-Vaya, G. Shih
Summary: This article describes a dataset used for the detection and localization of COVID-19 on chest radiographs, including the curation, annotation methodology, and characteristics. The dataset was annotated by an international group of radiologists and is available for academic and noncommercial use by researchers.
JOURNAL OF DIGITAL IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Junaid Mushtaq, Renato Pennella, Salvatore Lavalle, Anna Colarieti, Stephanie Steidler, Carlo M. A. Martinenghi, Diego Palumbo, Antonio Esposito, Patrizia Rovere-Querini, Moreno Tresoldi, Giovanni Landoni, Fabio Ciceri, Alberto Zangrillo, Francesco De Cobelli
Summary: The study evaluated the prognostic utility of an AI system assessing initial chest X-ray severity in patients with COVID-19, finding that patients with an AI system score of >= 30 had a higher risk of mortality and critical COVID-19. Additionally, RALE score, older age, male sex, coronary artery disease, COPD, and neurodegenerative disease were identified as independent predictors of adverse outcomes.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jin-Cao Yao, Tao Wang, Guang-Hua Hou, Di Ou, Wei Li, Qiao-Dan Zhu, Wen-Cong Chen, Chen Yang, Li-Jing Wang, Li-Ping Wang, Lin-Yin Fan, Kai-Yuan Shi, Jie Zhang, Dong Xu, Ya-Qing Li
Summary: The study utilized a deep learning model to accurately identify mild COVID-19 pneumonia from CT images, showing high sensitivity and specificity, with an AUC value of 0.955.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Eduardo J. Mortani Barbosa Jr, Warren B. Gefter, Florin C. Ghesu, Siqi Liu, Boris Mailhe, Awais Mansoor, Sasa Grbic, Sebastian Vogt
Summary: This study leveraged CT-derived volumetric quantification of airspace disease to train a CNN for quantifying AD on CXRs of patients with confirmed COVID-19. The CNN performed at a level comparable to expert human readers in quantifying AD on CXR.
INVESTIGATIVE RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jianhong Cheng, John Sollee, Celina Hsieh, Hailin Yue, Nicholas Vandal, Justin Shanahan, Ji Whae Choi, Thi My Linh Tran, Kasey Halsey, Franklin Iheanacho, James Warren, Abdullah Ahmed, Carsten Eickhoff, Michael Feldman, Eduardo Mortani Barbosa, Ihab Kamel, Cheng Ting Lin, Thomas Yi, Terrance Healey, Paul Zhang, Jing Wu, Michael Atalay, Harrison X. Bai, Zhicheng Jiao, Jianxin Wang
Summary: Deep learning models using longitudinal CXRs and clinical data were developed to predict in-hospital mortality for COVID-19 patients in the ICU. Models based on pre-ICU CXRs achieved an AUC of 0.632 and an accuracy of 0.593, models based on ICU CXRs achieved an AUC of 0.697 and an accuracy of 0.657, models based on all longitudinal CXRs achieved an AUC of 0.702 and an accuracy of 0.694, and models based on clinical data alone achieved an AUC of 0.653 and an accuracy of 0.657. The addition of longitudinal imaging to clinical data significantly improved mortality prediction, reaching an AUC of 0.727 and an accuracy of 0.732.
EUROPEAN RADIOLOGY
(2022)
Article
Biology
Aryan Verma, Sagar B. Amin, Muhammad Naeem, Monjoy Saha
Summary: This study proposes a novel Android application that detects COVID-19 infection from chest CT scans using a highly efficient and accurate deep learning algorithm. It also creates an attention heatmap to show the regions of infection in the lungs. The results show that the system achieves high accuracy and efficiency in the early diagnosis of COVID-19.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Aakarsh Malhotra, Surbhi Mittal, Puspita Majumdar, Saheb Chhabra, Kartik Thakral, Mayank Vatsa, Richa Singh, Santanu Chaudhury, Ashwin Pudrod, Anjali Agrawal
Summary: With the increasing number of COVID-19 cases globally, countries are ramping up testing numbers to find reliable, easily accessible, and faster alternate testing methods. This paper introduces the automated COVID-19 screening network COMiT-Net and manually annotates lung regions and COVID-19 symptoms with the help of medical professionals.
PATTERN RECOGNITION
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Isaac Shiri, Azadeh Akhavanallaf, Amirhossein Sanaat, Yazdan Salimi, Dariush Askari, Zahra Mansouri, Sajad P. Shayesteh, Mohammad Hasanian, Kiara Rezaei-Kalantari, Ali Salahshour, Saleh Sandoughdaran, Hamid Abdollahi, Hossein Arabi, Habib Zaidi
Summary: The study aimed to design a ultra-low-dose CT examination protocol for clinical diagnosis of COVID-19 patients using a deep learning approach. By utilizing a residual convolutional neural network, the study demonstrated the capability of predicting full-dose CT images with acceptable quality while substantially reducing radiation dose.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Toshimasa Matsumoto, Shoichi Ehara, Shannon L. Walston, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda
Summary: This study aimed to develop an artificial intelligence model to detect features of atrial fibrillation on chest radiographs. By training, tuning, and evaluating the model on different datasets, the study demonstrated the effectiveness and accuracy of the AI in identifying AF.
EUROPEAN RADIOLOGY
(2022)
Article
Computer Science, Information Systems
Muhammed Binsawad, Marwan Albahar, Abdullah Bin Sawad
Summary: The COVID-19 pandemic has had a devastating impact globally, highlighting the importance of effectively screening infected individuals, with chest X-rays being a key tool in this process. The introduction of VGG-COVIDNet, a novel neural network architecture for detecting COVID-19 cases from CXR images, has shown superior accuracy and sensitivity compared to existing models, with an accuracy and sensitivity of 96.5% and 96%, respectively, for each infection type.
CMC-COMPUTERS MATERIALS & CONTINUA
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jan Rudolph, Christian Huemmer, Florin-Cristian Ghesu, Awais Mansoor, Alexander Preuhs, Andreas Fieselmann, Nicola Fink, Julien Dinkel, Vanessa Koliogiannis, Vincent Schwarze, Sophia Goller, Maximilian Fischer, Maximilian Jorgens, Najib Ben Khaled, Reddappagari Suryanarayana Vishwanath, Abishek Balachandran, Michael Ingrisch, Jens Ricke, Bastian Oliver Sabel, Johannes Rueckel
Summary: This study introduces an artificial intelligence system that aims to assist non-radiology residents in interpreting chest radiographs in clinical settings. The system performs better than non-radiology residents in terms of diagnostic accuracy, as validated against board-certified radiologists and experienced residents.
INVESTIGATIVE RADIOLOGY
(2022)
Review
Health Care Sciences & Services
Roberta Fusco, Roberta Grassi, Vincenza Granata, Sergio Venanzio Setola, Francesca Grassi, Diletta Cozzi, Biagio Pecori, Francesco Izzo, Antonella Petrillo
Summary: The study provides an overview of AI and COVID-19 using chest CT and CXR images, emphasizing the high accuracy and precision of AI methods in diagnosing COVID-19. Despite variability, AI approaches show potential in disease identification, case monitoring, outbreak prediction, mortality risk assessment, diagnosis, and management of COVID-19.
JOURNAL OF PERSONALIZED MEDICINE
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Hirotaka Takita, Satoshi Doishita, Tetsuya Yoneda, Hiroyuki Tatekawa, Takato Abe, Yoshiaki Itoh, Daisuke Horiuchi, Taro Tsukamoto, Taro Shimono, Yukio Miki
Summary: This study investigated the association between PADRE imaging and amyloid PET in AD patients and normal controls. The results showed a significant correlation between the hypointense areas on PADRE imaging and the amyloid PET uptake, especially in the precuneus and cuneus.
MAGNETIC RESONANCE IN MEDICAL SCIENCES
(2023)
Article
Gastroenterology & Hepatology
Ken Kageyama, Akira Yamamoto, Atsushi Jogo, Etsuji Sohgawa, Shinichiro Izuta, Daisuke Himoto, Akihiko Kakimi, Ryuichi Kita, Yukio Miki
Summary: Reversed portal flow in patients with portosystemic shunts can be visualized on 4DCT. Factors contributing to reversed flow in the portal venous system include shunt originating from the splenic and superior mesenteric veins, worse albumin-bilirubin score, and smaller diameter of the main portal vein.
HEPATOLOGY RESEARCH
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Hiroyuki Tatekawa, Shu Matsushita, Daiju Ueda, Hirotaka Takita, Daisuke Horiuchi, Natsuko Atsukawa, Yuka Morishita, Taro Tsukamoto, Taro Shimono, Yukio Miki
Summary: The study evaluated the impact of reorientation of diffusion tensor imaging (DTI) data on the reproducibility of the ALPS index, which reflects the glymphatic function of the brain. The technique used in this study improved the reproducibility of the ALPS index, even in subjects with head rotation. However, it was found that rotation around the x axis may significantly affect the calculation of the ALPS index.
JAPANESE JOURNAL OF RADIOLOGY
(2023)
Article
Multidisciplinary Sciences
Takehito Nota, Ken Kageyama, Akira Yamamoto, Atsushi Jogo, Etsuji Sohgawa, Hiroki Yonezawa, Kazuki Murai, Satoyuki R. Ogawa, Yukio R. Miki, Vanessa R. Carels
Summary: This study evaluated the clinical outcomes of tract embolization using a gel-like radiopaque material and confirmed its viscosity and hemostatic efficacy. The results showed that tract embolization with this material is safe, feasible, and cost-effective.
Correction
Radiology, Nuclear Medicine & Medical Imaging
Taro Tsukamoto, Yukio Miki
JAPANESE JOURNAL OF RADIOLOGY
(2023)
Correction
Radiology, Nuclear Medicine & Medical Imaging
Taro Tsukamoto, Yukio Miki
JAPANESE JOURNAL OF RADIOLOGY
(2023)
Article
Clinical Neurology
Kosuke Okamoto, Akitoshi Takeda, Hiroyuki Hatsuta, Terunori Sano, Masaki Takao, Masahiko Ohsawa, Yukio Miki, Kazuo Nakamichi, Yoshiaki Itoh
Summary: This article reports a case of PML in a patient who developed bilateral visual disturbance and progressive aphasia after 16 months of treatment for follicular lymphoma. The MRI revealed white matter lesions with massive iron deposition. Autopsy findings confirmed the presence of abundant iron-laden macrophages and reactive astrocytes in the juxtacortical regions adjacent to the white matter lesions. This is the first reported case of PML after lymphoma with confirmed iron deposition.
Article
Clinical Neurology
Daisuke Horiuchi, Taro Shimono, Hiroyuki Tatekawa, Taro Tsukamoto, Hirotaka Takita, Shu Matsushita, Yukio Miki
Summary: Using MR diffusion-weighted imaging (DWI) thermometry, this study investigated the daily fluctuations in brain temperature in healthy individuals and examined the associations between brain and body temperatures and sex. The results showed that body temperatures were significantly higher in the evening compared to the morning, while no significant difference was observed in brain temperatures between the two phases. Multiple linear regression analysis revealed significant associations of morning brain temperature with sex, evening brain temperature, and the interaction between sex and evening brain temperature.
Review
Respiratory System
Takahiro Sugibayashi, Shannon L. Walston, Toshimasa Matsumoto, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda
Summary: This meta-analysis examined the application of deep learning in pneumothorax diagnosis and found that the diagnostic performance of deep learning models was similar to that of physicians, although the majority of studies had a high risk of bias.
EUROPEAN RESPIRATORY REVIEW
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Shu Matsushita, Hiroyuki Tatekawa, Daiju Ueda, Hirotaka Takita, Daisuke Horiuchi, Taro Tsukamoto, Taro Shimono, Yukio Miki
Summary: The aim of this study was to investigate the relationship between metabolic imaging measurements and clinical information in patients with Alzheimer's disease (AD) and normal controls (NCs). The results showed a positive correlation between brain temperature (BT) and the index of diffusivity along the perivascular space (ALPS index), while age was negatively correlated with ALPS index. However, no significant association was found between amyloid deposition in the cerebral cortex (measured by SUVR of amyloid PET) and BT or ALPS index.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Medical Informatics
Daiju Ueda, Toshimasa Matsumoto, Shoichi Ehara, Akira Yamamoto, Shannon L. Walston, Asahiro Ito, Taro Shimono, Masatsugu Shiba, Tohru Takeshita, Daiju Fukuda, Yukio Miki
Summary: This study developed and validated a deep learning model to detect valvular heart disease and cardiac function from chest radiographs. The model achieved accurate classification of various cardiac parameters such as left ventricular ejection fraction, tricuspid regurgitant velocity, and mitral regurgitation. It offers a fast and accessible alternative to echocardiography in areas with limited specialist availability.
LANCET DIGITAL HEALTH
(2023)
Article
Geriatrics & Gerontology
Yasuhito Mitsuyama, Toshimasa Matsumoto, Hiroyuki Tatekawa, Shannon L. Walston, Tatsuo Kimura, Akira Yamamoto, Toshio Watanabe, Yukio Miki, Daiju Ueda
Summary: This study aimed to develop a biomarker of ageing using chest radiography and examine its correlation with diseases. The results showed a strong correlation between the AI-estimated age and chronological age in healthy individuals. Furthermore, the difference between estimated age and chronological age correlated with various chronic diseases in individuals with known diseases.
LANCET HEALTHY LONGEVITY
(2023)
Article
Clinical Neurology
Daisuke Horiuchi, Hiroyuki Tatekawa, Taro Shimono, Shannon L. Walston, Hirotaka Takita, Shu Matsushita, Tatsushi Oura, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda
Summary: This study evaluated the diagnostic performance of GPT-4 based ChatGPT in neuroradiology. ChatGPT's diagnostic accuracy varied depending on disease etiologies, and its diagnostic accuracy was significantly lower in CNS tumors compared to non-CNS tumors.